© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77141
    Prev
    Next
    INDEX
    Explanations

    mentions of spiritual transformation and salvation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odzi
    -0.08
    obi
    -0.08
    ynchronize
    -0.07
    éĶ
    -0.07
    ulis
    -0.07
    ovit
    -0.07
    villa
    -0.07
    unsch
    -0.07
    argument
    -0.07
    ura
    -0.07
    POSITIVE LOGITS
     saving
    0.07
    -saving
    0.07
     saves
    0.06
     saved
    0.06
     amnesty
    0.06
     ÑģпаÑģ
    0.06
    å½Ĵ
    0.06
     Falk
    0.06
    .saved
    0.06
     Belle
    0.05
    Activations Density 0.020%

    No Known Activations